Developing supervised machine learning algorithms to evaluate the therapeutic effect and laboratory-related adverse events of cyclosporine and tacrolimus in renal transplants.

BACKGROUND

Single nucleotide polymorphisms influence the effects of tacrolimus and cyclosporine in renal transplants.

AIM

We set out to use machine learning algorithms (MLAs) to identify variables that predict the therapeutic effects and adverse events following tacrolimus and cyclosporine administration in renal transplant patients.

METHOD

We sampled 120 adult renal transplant patients (on cyclosporine or tacrolimus). Generalized linear model (GLM), support vector machine (SVM), artificial neural network (ANN), Chi-square automatic interaction detection, classification and regression tree, and K-nearest neighbors were the chosen MLAs. The mean absolute error (MAE), relative mean square error (RMSE), and regression coefficient (β) with a 95% confidence interval (CI) were used as the model parameters.

RESULTS

For a stable dose of tacrolimus, the MAEs (RMSEs) of GLM, SVM, and ANN were 1.3 (1.5), 1.3 (1.8), and 1.7 (2.3) mg/day, respectively. GLM revealed that the POR28 genotype and age significantly predicted the stable dose of tacrolimus as follows: POR28 (β -1.8; 95% CI -3, -0.5; p = 0.006), and age (β -0.04; 95% CI -0.1, -0.006; p = 0.02). For a stable dose of cyclosporine, MAEs (RMSEs) of 93.2 (103.4), 79.1 (115.2), and 73.7 (91.7) mg/day were observed with GLM, SVM, and ANN, respectively. GLM revealed the following predictors of a stable dose of cyclosporine: CYP3A5*3 (β -80.8; 95% CI -130.3, -31.2; p = 0.001), and age (β -3.4; 95% CI -5.9, -0.9; p = 0.007).

CONCLUSION

We observed that various MLAs could identify significant predictors that were useful to optimize tacrolimus and cyclosporine dosing regimens; yet, the findings must be externally validated.